> ## Documentation Index
> Fetch the complete documentation index at: https://docs.klio.tech/llms.txt
> Use this file to discover all available pages before exploring further.

# The handover loop

> Six movements that turn raw session activity into something the next agent can act on.

A shared text store is not a workplace. The difference is what happens between
one agent writing and the next one reading — six movements, of which the last
three are the ones a plain database will not do for you.

<Steps>
  <Step title="Clock in" icon="door-open">
    An agent connects over MCP and is resolved to an org, an agent identity, and
    optionally a space. No vendor owns the door — Claude Code, Cursor, Codex and
    your own agents all arrive the same way.
  </Step>

  <Step title="Capture" icon="pen-line">
    Work is recorded as it happens through `remember`, `decide`, `plan`,
    `observe`, and `note`. Secrets and personal data are stripped **before**
    anything is persisted, and that step fails closed.
  </Step>

  <Step title="File to the job" icon="folder-tree">
    Every write lands under an org, and optionally a space. The job's knowledge
    stays with the job rather than in one undifferentiated pile. See
    [Scope and spaces](/concepts/scope).
  </Step>

  <Step title="Distil" icon="filter">
    Raw activity is condensed into the few durable facts worth keeping. The next
    agent should inherit conclusions, not transcripts — a thousand observations
    are worth less than the one decision they led to.
  </Step>

  <Step title="Retire" icon="rotate-left">
    When a newer memory contradicts an older one, the old one is superseded
    rather than left to compete with it. This is the step almost nothing else
    does, and it is why recall stays sharp instead of degrading into a pile of
    mutually contradictory notes.
  </Step>

  <Step title="Hand over" icon="arrow-right-arrow-left">
    The next agent calls `recall` and receives current state. One writes; the
    next to look already sees it.
  </Step>
</Steps>

## Why distil and retire matter

Keeping text is easy. Two things make stored context stop being useful over
time, and both are the store's job to handle:

<AccordionGroup>
  <Accordion title="Volume drowns signal" icon="layer-group">
    An agent that logs every step produces thousands of low-value entries. Recall
    over that returns noise, and the model spends its context budget reading
    things that did not matter. Distilling means a session's worth of activity
    collapses into the handful of facts that survive it.
  </Accordion>

  <Accordion title="Old truth competes with new truth" icon="code-compare">
    Six months in, the store holds "we use fixed backoff" *and* "we use jittered
    backoff." Both surface. The agent picks one — sometimes the wrong one — and
    quietly undoes work. Superseding means the retired statement stops being
    returned, so nobody acts on stale truth.
  </Accordion>
</AccordionGroup>

## What the loop does not do

<Warning>
  Klio does not notify running agents. A write is available to the next agent
  that **reads**, immediately — but an agent already mid-session will not learn
  about it until it calls `recall` again. If you need two agents to coordinate
  within a single turn, that is a job for your orchestration layer, not for
  memory.
</Warning>

Nor does it decide what is worth keeping on your behalf. Agents write what they
are told to write. The prompt guidance in the [Quickstart](/quickstart#make-it-a-habit)
exists because a workplace where nobody writes anything down is just an empty
room.